{"total":114,"rows":[{"id":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214,"area":null},{"id":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","cited_by_count":136,"area":null},{"id":"2412.15322","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","created":"2024-12-19","cited_by_count":134,"area":null},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114,"area":null},{"id":"2407.01494","title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","created":"2024-07-01","cited_by_count":110,"area":null},{"id":"2211.12498","title":"Touch and Go: Learning from Human-Collected Vision and Touch","created":"2022-11-22","cited_by_count":87,"area":null},{"id":"2308.09300","title":"V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models","created":"2023-08-18","cited_by_count":65,"area":null},{"id":"2211.15058","title":"Mix and Localize: Localizing Sound Sources in Mixtures","created":"2022-11-28","cited_by_count":54,"area":null},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2304.08490","title":"Conditional Generation of Audio from Video via Foley Analogies","created":"2023-04-17","cited_by_count":52,"area":null},{"id":"2101.10803","title":"ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning","created":"2021-01-26","cited_by_count":50,"area":null},{"id":"2411.17698","title":"Video-Guided Foley Sound Generation with Multimodal Controls","created":"2024-11-26","cited_by_count":49,"area":null},{"id":"2407.05551","title":"Read, Watch and Scream! Sound Generation from Text and Video","created":"2024-07-08","cited_by_count":48,"area":null},{"id":"2104.06162","title":"Visually Informed Binaural Audio Generation without Binaural Audios","created":"2021-04-13","cited_by_count":46,"area":null},{"id":"2208.09579","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","created":"2022-08-20","cited_by_count":44,"area":null},{"id":"2210.12649","title":"Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation","created":"2022-10-23","cited_by_count":41,"area":null},{"id":"2303.17490","title":"Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment","created":"2023-03-30","cited_by_count":41,"area":null},{"id":"2401.08577","title":"MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World","created":"2024-01-16","cited_by_count":39,"area":null},{"id":"2411.05679","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","created":"2024-11-08","cited_by_count":34,"area":null},{"id":"2403.05659","title":"Audio-Synchronized Visual Animation","created":"2024-03-08","cited_by_count":32,"area":null},{"id":"2104.06401","title":"Self-supervised object detection from audio-visual correspondence","created":"2021-04-13","cited_by_count":29,"area":null},{"id":"2109.11955","title":"Visual Scene Graphs for Audio Source Separation","created":"2021-09-24","cited_by_count":29,"area":null},{"id":"2212.03814","title":"iQuery: Instruments as Queries for Audio-Visual Sound Separation","created":"2022-12-07","cited_by_count":29,"area":null},{"id":"2407.10387","title":"Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity","created":"2024-07-15","cited_by_count":28,"area":null},{"id":"2104.13332","title":"End-to-End Video-To-Speech Synthesis using Generative Adversarial Networks","created":"2021-04-27","cited_by_count":27,"area":null},{"id":"2405.04534","title":"Tactile-Augmented Radiance Fields","created":"2024-05-07","cited_by_count":26,"area":null},{"id":"2108.00688","title":"Self-supervised Audiovisual Representation Learning for Remote Sensing Data","created":"2021-08-02","cited_by_count":24,"area":null},{"id":"2205.09248","title":"MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes","created":"2022-05-18","cited_by_count":23,"area":null},{"id":"2409.19132","title":"From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation","created":"2024-09-27","cited_by_count":23,"area":null},{"id":"2111.10882","title":"Geometry-Aware Multi-Task Learning for Binaural Audio Generation from Video","created":"2021-11-21","cited_by_count":22,"area":null},{"id":"2205.05072","title":"Learning Visual Styles from Audio-Visual Associations","created":"2022-05-10","cited_by_count":22,"area":null},{"id":"2406.09272","title":"Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videos","created":"2024-06-13","cited_by_count":21,"area":null},{"id":"2107.09262","title":"FoleyGAN: Visually Guided Generative Adversarial Network-Based Synchronous Sound Generation in Silent Videos","created":"2021-07-20","cited_by_count":20,"area":null},{"id":"2206.07148","title":"It's Time for Artistic Correspondence in Music and Video","created":"2022-06-14","cited_by_count":18,"area":null},{"id":"2303.11329","title":"Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation","created":"2023-03-20","cited_by_count":18,"area":null},{"id":"2305.06594","title":"V2Meow: Meowing to the Visual Beat via Video-to-Music Generation","created":"2023-05-11","cited_by_count":18,"area":null},{"id":"2111.05846","title":"Structure from Silence: Learning Scene Structure from Ambient Sound","created":"2021-11-10","cited_by_count":17,"area":null},{"id":"2310.12904","title":"Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey","created":"2023-10-19","cited_by_count":16,"area":null},{"id":"2408.11915","title":"Video-Foley: Two-Stage Video-To-Sound Generation via Temporal Event Condition For Foley Sound","created":"2024-08-21","cited_by_count":16,"area":null},{"id":"2303.16541","title":"Sounding Video Generator: A Unified Framework for Text-guided Sounding Video Generation","created":"2023-03-29","cited_by_count":15,"area":null},{"id":"2308.12370","title":"AdVerb: Visually Guided Audio Dereverberation","created":"2023-08-23","cited_by_count":15,"area":null},{"id":"2409.07450","title":"VMAS: Video-to-Music Generation via Semantic Alignment in Web Music Videos","created":"2024-09-11","cited_by_count":15,"area":null},{"id":"2105.00708","title":"Exploiting Audio-Visual Consistency with Partial Supervision for Spatial Audio Generation","created":"2021-05-03","cited_by_count":14,"area":null},{"id":"2207.03483","title":"Finding Fallen Objects Via Asynchronous Audio-Visual Integration","created":"2022-07-07","cited_by_count":14,"area":null},{"id":"2210.01116","title":"That Sounds Right: Auditory Self-Supervision for Dynamic Robot Manipulation","created":"2022-10-03","cited_by_count":12,"area":null},{"id":"2210.16472","title":"Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation","created":"2022-10-29","cited_by_count":11,"area":null},{"id":"2211.10666","title":"VarietySound: Timbre-Controllable Video to Sound Generation via Unsupervised Information Disentanglement","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2404.05206","title":"SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos","created":"2024-04-08","cited_by_count":11,"area":null},{"id":"2409.05427","title":"TextToucher: Fine-Grained Text-to-Touch Generation","created":"2024-09-09","cited_by_count":11,"area":null},{"id":"2506.12199","title":"ViSAGe: Video-to-Spatial Audio Generation","created":"2025-06-13","cited_by_count":11,"area":null},{"id":"2306.09944","title":"RealImpact: A Dataset of Impact Sound Fields for Real Objects","created":"2023-06-16","cited_by_count":9,"area":null},{"id":"2207.10760","title":"A Proposal for Foley Sound Synthesis Challenge","created":"2022-07-21","cited_by_count":8,"area":null},{"id":"2301.02184","title":"Chat2Map: Efficient Scene Mapping from Multi-Ego Conversations","created":"2023-01-04","cited_by_count":8,"area":null},{"id":"2307.04760","title":"Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos","created":"2023-07-10","cited_by_count":8,"area":null},{"id":"2409.14340","title":"Self-Supervised Audio-Visual Soundscape Stylization","created":"2024-09-22","cited_by_count":8,"area":null},{"id":"2409.06135","title":"Draw an Audio: Leveraging Multi-Instruction for Video-to-Audio Synthesis","created":"2024-09-10","cited_by_count":7,"area":null},{"id":"2511.13219","title":"FoleyBench: A Benchmark For Video-to-Audio Models","created":"2025-11-17","cited_by_count":7,"area":null},{"id":"2104.02656","title":"Collaborative Learning to Generate Audio-Video Jointly","created":"2021-04-01","cited_by_count":6,"area":null},{"id":"2107.05468","title":"Visual-Tactile Cross-Modal Data Generation using Residue-Fusion GAN with Feature-Matching and Perceptual Losses","created":"2021-07-12","cited_by_count":6,"area":null},{"id":"2112.09726","title":"Soundify: Matching Sound Effects to Video","created":"2021-12-17","cited_by_count":6,"area":null},{"id":"2308.16900","title":"Learning to Taste: A Multimodal Wine Dataset","created":"2023-08-31","cited_by_count":6,"area":null},{"id":"2507.02864","title":"The Sound of Simulation: Learning Multimodal Sim-to-Real Robot Policies with Generative Audio","created":"2025-07-03","cited_by_count":6,"area":null},{"id":"2201.01046","title":"Sound and Visual Representation Learning with Multiple Pretraining Tasks","created":"2022-01-04","cited_by_count":5,"area":null},{"id":"2412.06209","title":"Sound2Vision: Generating Diverse Visuals from Audio through Cross-Modal Latent Alignment","created":"2024-12-09","cited_by_count":5,"area":null},{"id":"2412.15023","title":"FolAI: Synchronized Foley Sound Generation with Semantic and Temporal Alignment","created":"2024-12-19","cited_by_count":5,"area":null},{"id":"2505.12154","title":"Learning to Highlight Audio by Watching Movies","created":"2025-05-17","cited_by_count":5,"area":null},{"id":"2102.03503","title":"Template-Free Try-on Image Synthesis via Semantic-guided Optimization","created":"2021-02-06","cited_by_count":4,"area":null},{"id":"2109.02763","title":"Binaural SoundNet: Predicting Semantics, Depth and Motion with Binaural Sounds","created":"2021-09-06","cited_by_count":4,"area":null},{"id":"2502.12489","title":"A Comprehensive Survey on Generative AI for Video-to-Music Generation","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2505.19614","title":"Multiplicity is an Inevitable and Inherent Challenge in Multimodal Learning","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2508.03955","title":"Scaling Up Audio-Synchronized Visual Animation: An Efficient Training Paradigm","created":"2025-08-05","cited_by_count":4,"area":null},{"id":"2603.15597","title":"AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2105.08052","title":"The Boombox: Visual Reconstruction from Acoustic Vibrations","created":"2021-05-17","cited_by_count":3,"area":null},{"id":"2304.05600","title":"Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2506.04214","title":"Sounding that Object: Interactive Object-Aware Image to Audio Generation","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2511.20544","title":"New York Smells: A Large Multimodal Dataset for Olfaction","created":"2025-11-25","cited_by_count":3,"area":null},{"id":"2603.28757","title":"SonoWorld: From One Image to a 3D Audio-Visual Scene","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2211.11381","title":"LISA: Localized Image Stylization with Audio via Implicit Neural Representation","created":"2022-11-21","cited_by_count":2,"area":null},{"id":"2506.09989","title":"Hearing Hands: Generating Sounds from Physical Interactions in 3D Scenes","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2512.02457","title":"Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation","created":"2025-12-02","cited_by_count":2,"area":null},{"id":"2603.11042","title":"V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2605.30339","title":"Benchmarking Single-Factor Physical Video-to-Audio Generation","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2108.04529","title":"Hand Pose Classification Based on Neural Networks","created":"2021-08-10","cited_by_count":1,"area":null},{"id":"2202.05961","title":"Audio-Visual Fusion Layers for Event Type Aware Video Recognition","created":"2022-02-12","cited_by_count":1,"area":null},{"id":"2308.11859","title":"Example-Based Framework for Perceptually Guided Audio Texture Generation","created":"2023-08-23","cited_by_count":1,"area":null},{"id":"2311.07630","title":"Cross-modal Generative Model for Visual-Guided Binaural Stereo Generation","created":"2023-11-13","cited_by_count":1,"area":null},{"id":"2409.13507","title":"Sketching With Your Voice: \"Non-Phonorealistic\" Rendering of Sounds via Vocal Imitation","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2411.15447","title":"Gotta Hear Them All: Towards Sound Source Aware Audio Generation","created":"2024-11-23","cited_by_count":1,"area":null},{"id":"2503.24270","title":"Visual Acoustic Fields","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2508.17376","title":"ShaLa: Multimodal Shared Latent Space Modelling","created":"2025-08-24","cited_by_count":1,"area":null},{"id":"2603.14203","title":"Selective Noise Suppression and Discriminative Mutual Interaction for Robust Audio-Visual Segmentation","created":"2026-03-15","cited_by_count":1,"area":null},{"id":"2108.11773","title":"Multi-Modulation Network for Audio-Visual Event Localization","created":"2021-08-26","cited_by_count":0,"area":null},{"id":"2111.02322","title":"A Comparison of Deep Learning Models for the Prediction of Hand Hygiene Videos","created":"2021-11-03","cited_by_count":0,"area":null},{"id":"2205.05895","title":"Weakly-Supervised Action Detection Guided by Audio Narration","created":"2022-05-12","cited_by_count":0,"area":null},{"id":"2212.02978","title":"Muscles in Action","created":"2022-12-05","cited_by_count":0,"area":null},{"id":"2301.11745","title":"Side Auth: Synthesizing Virtual Sensors for Authentication","created":"2023-01-27","cited_by_count":0,"area":null},{"id":"2305.20046","title":"Assessing Language Disorders using Artificial Intelligence: a Paradigm Shift","created":"2023-05-31","cited_by_count":0,"area":null},{"id":"2410.18932","title":"ANAVI: Audio Noise Awareness using Visuals of Indoor environments for NAVIgation","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2412.07406","title":"Learning Self-Supervised Audio-Visual Representations for Sound Recommendations","created":"2024-12-10","cited_by_count":0,"area":null},{"id":"2505.12734","title":"SounDiT: Geo-Contextual Soundscape-to-Landscape Generation","created":"2025-05-19","cited_by_count":0,"area":null}],"next_cursor":"100"}